Instructions to use DevQuasar-2/falcon2-11B_chat_brainstorm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DevQuasar-2/falcon2-11B_chat_brainstorm with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DevQuasar-2/falcon2-11B_chat_brainstorm", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DevQuasar-2/falcon2-11B_chat_brainstorm", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("DevQuasar-2/falcon2-11B_chat_brainstorm", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DevQuasar-2/falcon2-11B_chat_brainstorm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DevQuasar-2/falcon2-11B_chat_brainstorm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DevQuasar-2/falcon2-11B_chat_brainstorm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DevQuasar-2/falcon2-11B_chat_brainstorm

SGLang

How to use DevQuasar-2/falcon2-11B_chat_brainstorm with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DevQuasar-2/falcon2-11B_chat_brainstorm" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DevQuasar-2/falcon2-11B_chat_brainstorm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DevQuasar-2/falcon2-11B_chat_brainstorm" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DevQuasar-2/falcon2-11B_chat_brainstorm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DevQuasar-2/falcon2-11B_chat_brainstorm with Docker Model Runner:
```
docker model run hf.co/DevQuasar-2/falcon2-11B_chat_brainstorm
```

'Make knowledge free for everyone'

falcon-11B):

"The model is made available under the TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI."

Examples

Inference code

https://github.com/csabakecskemeti/ai_utils/blob/main/brainstorm_falcon11b_inference.py

Usage

python brainstorm_falcon11b_inference.py DevQuasar/falcon2-11B_chat_brainstorm

Example generations

[USER] (Ctrl+C to exit): I'd like to start a company that sells unique tshirts with AI generated resign

[CHAT]: That sounds interesting! What kind of technology would you use to create these shirts? Would it be something new or existing? And how do you plan to incorporate the AI into the design?

[USER] (Ctrl+C to exit):

I think I'd user existing tshirst print services. 2) Not wure what you mean 'Would it be something new or existing?' 3) I plan to use a a commerically available image generator like dall-e

[CHAT]: Wow, that's quite advanced! Have you considered how you'll handle the logistics of shipping and handling for these specialty garments? Will you partner with existing suppliers or develop your own manufacturing process?' What kind of customer service would you provide? And how would you ensure that the AI technology is scalable and adaptable to different production methods?

[USER] (Ctrl+C to exit): Use the postal service and direct ship from the print service. Yes I believe AI would be scalable.

[CHAT]: That makes sense. How do you envision the AI system working? Would it be integrated with traditional fashion brands or independent retailers? Or would you see this happening in the future?

I'm doing this to 'Make knowledge free for everyone', using my personal time and resources.

If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar

Also feel free to visit my website https://devquasar.com/

Downloads last month: 11

Safetensors

Model size

11B params

Tensor type

F32

Model tree for DevQuasar-2/falcon2-11B_chat_brainstorm

Base model

tiiuae/falcon-11B

Finetuned

(18)

this model

DevQuasar-2
/

falcon2-11B_chat_brainstorm